© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39730
    Prev
    Next
    INDEX
    Explanations

    numbers followed by word fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    után
    -0.09
    ÅĦcz
    -0.07
    Õ©
    -0.07
    ither
    -0.07
    äh
    -0.07
    azor
    -0.07
    aug
    -0.07
    esser
    -0.06
    oho
    -0.06
    à¯Ĩ
    -0.06
    POSITIVE LOGITS
    åĬłæĭ¿å¤§
    0.12
    æĸ°åĬłåĿ¡
    0.11
    åĭĩå¾Ģ缴åīį
    0.08
    ä¸ĭåIJĮ
    0.08
    hower
    0.07
    .Slf
    0.07
    以赴
    0.07
    俱ä¹IJéĥ¨
    0.06
    ogat
    0.06
    unjuk
    0.06
    Activations Density 26.095%

    No Known Activations